© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 28120
    Prev
    Next
    INDEX
    Explanations

    physical addresses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    insk
    -0.07
     esti
    -0.07
    å¤ļç§įå½¢å¼ı
    -0.06
    itta
    -0.06
    ankind
    -0.06
    iris
    -0.06
    itano
    -0.06
    _PROTOCOL
    -0.06
    èİĵ
    -0.06
     typeof
    -0.06
    POSITIVE LOGITS
    ¹Ħ
    0.08
    elm
    0.08
     ÑħоÑĤÑı
    0.08
    æĮ¨
    0.07
    rex
    0.07
    icto
    0.07
    èĻ½çĦ¶ä¸įæĺ¯
    0.07
    å¤§æľ¬
    0.07
    åľ¨ä¸ĬéĿ¢
    0.07
    chau
    0.07
    Activations Density 0.004%

    No Known Activations